Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-17 17:10 |
Okinawa |
Okinawa Institute of Science and Technology |
MCMC for Value-at-Risk estimation Igor Zavialov, Kazushi Ikeda (NAIST) NC2019-11 |
Value-at-Risk models (VaR) are powerful tools for financial risk management and are widely used by regulating authoritie... [more] |
NC2019-11 pp.41-44 |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-17 17:35 |
Okinawa |
Okinawa Institute of Science and Technology |
Mental Disorder Diagnosis Based on fMRI Images by Deep Privileged Attribute Model Koki Kusano, Tetsuo Tashiro, Takashi Matsubara, Kuniaki Uehara (Kobe Univ.) NC2019-12 |
Machine learning-based accurate diagnosis of mental disorders is expected to support finding their biomarkers and unders... [more] |
NC2019-12 pp.45-50 |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-18 10:25 |
Okinawa |
Okinawa Institute of Science and Technology |
Spatial-Temporal decomposition to resting and task MEG using DMD Fumiya Nakai (NAIST), Okito Yamashita (ATR) NC2019-13 IBISML2019-11 |
Magneto/electroencephalography (M/EEG) observe neural activities with high spatial-temporal resolution without invasive ... [more] |
NC2019-13 IBISML2019-11 pp.51-56(NC), pp.73-78(IBISML) |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-18 10:50 |
Okinawa |
Okinawa Institute of Science and Technology |
A sleep state analysis from calcium imaging data using non-negative matrix factorization Mizuo Nagayama, Toshimitsu Aritake (Waseda Univ.), Hideitsu Hino (ISM), Takeshi Kanda, Takehiro Miyazaki, Masashi Yanagisawa (Univ. of Tsukuba), Shotaro Akaho (AIST), Noboru Murata (Waseda Univ.) NC2019-14 IBISML2019-12 |
Sleep is an essential process for the survival of animals, however, its phenomenon is poorly understood. We aim to disco... [more] |
NC2019-14 IBISML2019-12 pp.57-61(NC), pp.79-83(IBISML) |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-18 11:15 |
Okinawa |
Okinawa Institute of Science and Technology |
Detection of Syntactic Anomalies in Spoken Sentences from Single-trial EEG Signals with Neural Networks Shunnosuke Motomura, Hiroki Tanaka, Satoshi Nakamura (NAIST) NC2019-15 IBISML2019-13 |
In this paper we propose a method with neural networks for detecting syntactic anomalies in sentences using electroencep... [more] |
NC2019-15 IBISML2019-13 pp.63-68(NC), pp.85-90(IBISML) |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-18 13:30 |
Okinawa |
Okinawa Institute of Science and Technology |
Hybrid Reinforcement and Imitation Learning for Human-Like Agents Rousslan Fernand Julien Dossa, Xinyu Lian (Kobe Uni), Hirokazu Nomoto (EQUOS RESEARCH), Takashi Matsubara, Kuniaki Uehara (Kobe Uni) NC2019-16 IBISML2019-14 |
Reinforcement learning methods achieve performance superior to humans in a wide range of complex tasks and uncertain env... [more] |
NC2019-16 IBISML2019-14 pp.69-74(NC), pp.91-96(IBISML) |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-18 13:55 |
Okinawa |
Okinawa Institute of Science and Technology |
Additive or Concatenating Skip-connections Overcome the Degradation Problem of the Classic Feedforward Neural Network Yasutaka Furusho, Kazushi Ikeda (NAIST) NC2019-17 IBISML2019-15 |
The classic feedforward neural networks like the multilayer perceptron (MLP) degrades its empirical risk by training eve... [more] |
NC2019-17 IBISML2019-15 pp.75-80(NC), pp.97-102(IBISML) |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-18 14:20 |
Okinawa |
Okinawa Institute of Science and Technology |
ResNet and Batch-normalization Improve Data Separation Ability Yasutaka Furusho, Kazushi Ikeda (NAIST) NC2019-18 IBISML2019-16 |
The skip-connection and the batch-normalization (BN) in ResNet enable an extreme deep neural network to be trained with ... [more] |
NC2019-18 IBISML2019-16 pp.81-86(NC), pp.103-108(IBISML) |
NC, IBISML, IPSJ-MPS, IPSJ-BIO [detail] |
2019-06-18 14:45 |
Okinawa |
Okinawa Institute of Science and Technology |
Theoretical Analysis of the Fixup Initialization for Fast Convergence and High Generalization Ability Yasutaka Furusho, Kazushi Ikeda (NAIST) NC2019-19 IBISML2019-17 |
The Fixup initialization is a new initialization method of ResNet for a fast convergence with a high learning rate of SG... [more] |
NC2019-19 IBISML2019-17 pp.87-92(NC), pp.109-114(IBISML) |